Commit Graph

305 Commits

Author SHA1 Message Date
Xuan Son Nguyen c1dfccd078 Merge branch 'master' into xsn/server_model_management_v1_2 2025-11-29 22:34:16 +01:00
Xuan-Son Nguyen ab49f094d2
server: move server-context to its own cpp|h (#17595)
* git mv

* add server-context.h

* add server-context.h

* clean up headers

* cont : cleanup

* also expose server_response_reader (to be used by CLI)

* fix windows build

* decouple server_routes and server_http

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-11-29 22:04:44 +01:00
Haiyue Wang 8c32d9d96d
server: explicitly set the function name in lambda (#17538)
As [1] explained, the real debug message will be like:
	"res    operator(): operator() : queue result stop"

Set the name explicitly, the message is easy for debugging:
	"res    operator(): recv : queue result stop"

The left "operator()" is generated by 'RES_DBG() ... __func__'

[1]: https://clang.llvm.org/extra/clang-tidy/checks/bugprone/lambda-function-name.html

Signed-off-by: Haiyue Wang <haiyuewa@163.com>
2025-11-29 18:43:29 +01:00
Igor Smirnov 0874693b44
common : fix json schema with '\' in literals (#17307)
* Fix json schema with '\' in literals

* Add "literal string with escapes" test
2025-11-29 17:06:32 +01:00
o7si 3ce7a65c2f
server: fix: /metrics endpoint returning JSON-escaped Prometheus format (#17386)
* fix: /metrics endpoint returning JSON-escaped Prometheus format

* mod: remove string overload from ok() method
2025-11-28 19:14:00 +01:00
Xuan Son Nguyen 7be833dacc add TODO for http client 2025-11-28 13:10:44 +01:00
Xuan Son Nguyen bdaf44a13c Merge branch 'master' into xsn/server_model_management_v1_2 2025-11-28 13:07:36 +01:00
Fredrik Hultin ddf9f94389
server : add Anthropic Messages API support (#17570)
* server : add Anthropic Messages API support

* remove -@pytest.mark.slow from tool calling/jinja tests

* server : remove unused code and slow/skip on test_anthropic_vision_base64_with_multimodal_model in test_anthropic_api.py

* server : removed redundant n field logic in anthropic_params_from_json

* server : use single error object instead of error_array in streaming response handler for /v1/chat/completions and use unordered_set instead of set in to_json_anthropic_stream()

* server : refactor Anthropic API to use OAI conversion

* make sure basic test always go first

* clean up

* clean up api key check, add test

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2025-11-28 12:57:04 +01:00
Xuan-Son Nguyen e509411cf1
server: enable jinja by default, update docs (#17524)
* server: enable jinja by default, update docs

* fix tests
2025-11-27 01:02:50 +01:00
Xuan Son Nguyen 1493ee09ea tmp webui build 2025-11-26 17:43:27 +01:00
Xuan Son Nguyen becc602612 Merge branch 'master' into xsn/server_model_management_v1_2 2025-11-26 16:21:57 +01:00
Xuan Son Nguyen e2731c3767 set hf_repo/docker_repo as model alias when posible 2025-11-26 15:57:20 +01:00
Xuan Son Nguyen e40f35fb61 remove support for extra args 2025-11-26 15:43:27 +01:00
Pascal b1846f1c8e
webui: add rehype plugin to restore HTML in Markdown table cells (#17477)
* webui: add rehype plugin to restore HTML in Markdown table cells

The remark/rehype pipeline neutralizes inline HTML as literal text
(remarkLiteralHtml) so that XML/HTML snippets in LLM responses display
as-is instead of being rendered. This causes <br> and <ul> markup in
table cells to show as plain text.

This plugin traverses the HAST post-conversion, parses whitelisted HTML
patterns (<br>, <ul><li>) from text nodes, and replaces them with actual
HAST element nodes. For lists, adjacent siblings must be combined first
as the AST fragmentation breaks pattern matching.

Strict validation rejects malformed markup, keeping it as raw text.

* chore: update webui build output
2025-11-25 08:01:02 +01:00
Xuan Son Nguyen e514b86d2b fix merge 2025-11-24 14:50:42 +01:00
Xuan Son Nguyen 399b39f21b Merge branch 'master' into xsn/server_model_management_v1_2 2025-11-24 14:45:57 +01:00
Xuan-Son Nguyen b8372eecd9
server: split server.cpp code into server/common/task/queue (#17362)
* add server-task, server-common

* add server-queue

* rm redundant includes

* move enum stop_type to server-task

* server : headers cleanup

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-11-24 14:41:53 +01:00
Xuan Son Nguyen 539cbf003e add stdin_file 2025-11-24 14:21:21 +01:00
Xuan Son Nguyen 2c6b58f785 nits 2025-11-24 12:20:34 +01:00
Xuan Son Nguyen 6ed192b4dd add --models-allow-extra-args for security 2025-11-24 12:01:16 +01:00
Aleksander Grygier 5ef3f990b9 chore: update webui build output 2025-11-24 02:24:27 +01:00
Aleksander Grygier b2590a7f6c refactor: Cleanup 2025-11-24 02:24:10 +01:00
Aleksander Grygier 13fe8607c5 refactor: Cleanup 2025-11-24 01:42:42 +01:00
Aleksander Grygier 76557cd5d3 Merge remote-tracking branch 'ngxson/xsn/server_model_management_v1_2' into allozaur/server_model_management_v1_2 2025-11-24 00:36:00 +01:00
Aleksander Grygier e808f2b2e6 chore: update webui build output 2025-11-23 23:45:08 +01:00
Aleksander Grygier 16747dee5b refactor: UI badges 2025-11-23 23:44:14 +01:00
Aleksander Grygier 188d3236e4 chore: update webui build output 2025-11-23 23:28:49 +01:00
Aleksander Grygier 39fb1c2b17 refactor: Cleanup 2025-11-23 23:28:28 +01:00
Aleksander Grygier fb5445e9ce chore: update webui build output 2025-11-23 23:25:05 +01:00
Aleksander Grygier e92ce07916 refactor: Copy To Clipboard Icon component 2025-11-23 23:23:38 +01:00
Aleksander Grygier 219fd19eb8 chore: update webui build output 2025-11-23 23:09:09 +01:00
Aleksander Grygier 41764b8fa0 refactor: Formatters 2025-11-23 22:54:14 +01:00
Aleksander Grygier f8ff39c64e refactor: Cleanup 2025-11-23 22:32:31 +01:00
Aleksander Grygier d5a6671b81 refactor: Cleanup 2025-11-23 22:27:25 +01:00
Aleksander Grygier 49c8062db1 chore: update webui build output 2025-11-23 22:25:34 +01:00
Aleksander Grygier ef5f9d07b0 feat: Improve Model Selector responsiveness 2025-11-23 22:23:50 +01:00
Aleksander Grygier 1c214e9a49 refactor: Enum imports 2025-11-23 22:16:22 +01:00
Aleksander Grygier 48dbef1729 chore: update webui build output 2025-11-23 21:58:38 +01:00
Aleksander Grygier b7ba13b6a0 refactor: Attachments data 2025-11-23 21:46:43 +01:00
Aleksander Grygier 1f0cb3ab26 feat: Use `model` property for displaying the `repo/model-name` naming format 2025-11-23 21:19:00 +01:00
Xuan Son Nguyen d65be9170b address review comments 2025-11-23 19:31:21 +01:00
Xuan Son Nguyen 5ad594e6d6 cleaner 2025-11-23 19:02:07 +01:00
Pascal 0c7220db56
webui: minor settings reorganization and add disable autoscroll option (#17452)
* webui: added a dedicated 'Display' settings section that groups visualization options

* webui: added a Display setting to toggle automatic chat scrolling

* chore: update webui build output
2025-11-23 18:42:00 +01:00
Xuan Son Nguyen 2e355c7f8e oai-compat /models endpoint 2025-11-23 17:25:24 +01:00
Xuan Son Nguyen f95f9c5128 typo docs 2025-11-23 16:14:02 +01:00
Xuan Son Nguyen 74685f4194 allow reusing args if auto_load 2025-11-23 15:42:33 +01:00
Xuan Son Nguyen f927e21ffc support extra_args on loading model 2025-11-23 15:39:03 +01:00
Xuan Son Nguyen 7ef6312f85 add note 2025-11-23 15:08:31 +01:00
Xuan Son Nguyen f25bfaba4d expose args and exit_code in API 2025-11-23 14:59:04 +01:00
Aleksander Grygier 6282537a8b Merge remote-tracking branch 'ngxson/xsn/server_model_management_v1_2' into allozaur/server_model_management_v1_2 2025-11-22 23:35:05 +01:00